Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 24332
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    facility
    -0.06
     draining
    -0.06
     LOGGER
    -0.06
     JO
    -0.06
    rift
    -0.06
     pohod
    -0.06
     dio
    -0.06
    isto
    -0.06
    iors
    -0.06
     autofocus
    -0.06
    POSITIVE LOGITS
     recursos
    0.07
    ,’’
    0.07
     Его
    0.07
     Thị
    0.07
    часно
    0.06
    _EXECUTE
    0.06
     E
    0.06
    .addRow
    0.06
    -hooks
    0.06
    [:]
    0.06
    Activations Density 0.268%

    No Known Activations